© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10836
    Prev
    Next
    INDEX
    Explanations

    higher education organizations and people affiliated with them

    oai_token-act-pair · gemini-2.0-flash

    institute or collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.68
    Pautan
    -0.61
    
    -0.59
     unknownFields
    -0.58
    DebuggerStep
    -0.56
    kraut
    -0.56
    ώς
    -0.54
    BagConstraints
    -0.53
    swick
    -0.53
    KommentareTeilen
    -0.53
    POSITIVE LOGITS
    onViewCreated
    0.66
    Slf
    0.55
     fleste
    0.55
    lccn
    0.50
     jspb
    0.49
    InjectAttribute
    0.49
    XtraEditors
    0.49
     rígido
    0.49
     surpresa
    0.47
     Maat
    0.46
    Activations Density 1.188%

    No Known Activations